{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T15:00:40Z","timestamp":1791644440861,"version":"4.3.4"},"reference-count":67,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T00:00:00Z","timestamp":1744416000000},"content-version":"vor","delay-in-days":11,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["alz-journals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Alzheimer's &amp;amp; Dementia"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>INTRODUCTION<\/jats:title>\n                    <jats:p>Leveraging routinely collected electronic health records (EHRs) from multiple health\u2010care institutions, this approach aims to assess the feasibility of using federated learning (FL) to predict the progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>We analyzed EHR data from the OneFlorida+ consortium, simulating six sites, and used a long short\u2010term memory (LSTM) model with a federated averaging (FedAvg) algorithm. A personalized FL approach was used to address between\u2010site heterogeneity. Model performance was assessed using the area under the receiver operating characteristic curve (AUC) and feature importance techniques.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>Of 44,899 MCI patients, 6391 progressed to AD. FL models achieved a 6% improvement in AUC compared to local models. Key predictive features included body mass index, vitamin B12, blood pressure, and others.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>DISCUSSION<\/jats:title>\n                    <jats:p>FL showed promise in predicting AD progression by integrating heterogeneous data across multiple institutions while preserving privacy. Despite limitations, it offers potential for future clinical applications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Highlights<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>We applied long short\u2010term memory and federated learning (FL) to predict mild cognitive impairment to Alzheimer's disease progression using electronic health record data from multiple institutions.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>FL improved prediction performance, with a 6% increase in area under the receiver operating characteristic curve compared to local models.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>We identified key predictive features, such as body mass index, vitamin B12, and blood pressure.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>FL shows effectiveness in handling data heterogeneity across multiple sites while ensuring data privacy.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Personalized and pooled FL models generally performed better than global and local models.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/alz.70128","type":"journal-article","created":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T06:25:36Z","timestamp":1744439136000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Federated learning with multi\u2010cohort real\u2010world data for predicting the progression from mild cognitive impairment to Alzheimer's disease"],"prefix":"10.1002","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0695-9896","authenticated-orcid":false,"given":"Jinqian","family":"Pan","sequence":"first","affiliation":[{"name":"Department of Health Outcomes &amp; Biomedical Informatics University of Florida Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengkang","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes &amp; Biomedical Informatics University of Florida Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Glenn E.","family":"Smith","sequence":"additional","affiliation":[{"name":"Department of Clinical and Health Psychology University of Florida Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes &amp; Biomedical Informatics University of Florida Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Bian","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Data Science Indiana University Indianapolis Indiana USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5291-5198","authenticated-orcid":false,"given":"Jie","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes &amp; Biomedical Informatics University of Florida Gainesville Florida USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,4,12]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2012.02.001"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a006148"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1092852918001347"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/joim.12190"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1001\/archneurol.2009.106"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp.2007.142679"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-38793-3"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-019-0485-0"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2021.688926"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12883-020-01728-x"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0138866"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-020-00716-0"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2010.05.023"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/alz.12967"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0256-0"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/hsr2.1438"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.14283\/jpad.2023.10"},{"key":"e_1_2_10_19_1","doi-asserted-by":"crossref","unstructured":"BeeklyDL RamosEM LeeWW et\u00a0al.The national alzheimer's coordinating center (NACC) database: the uniform data set.2007:249\u2010258.","DOI":"10.1097\/WAD.0b013e318142774e"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.01.007"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41666-020-00082-4"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.7744"},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","unstructured":"XuJ XuZ WalkerP WangF. Federated patient hashing.In Proc AAAI Conf Artif Intell.2020:6486\u20106493.","DOI":"10.1609\/aaai.v34i04.6121"},{"key":"e_1_2_10_25_1","doi-asserted-by":"crossref","unstructured":"KimY SunJ YuH JiangX. Federated tensor factorization for computational phenotyping.In Proc 23rd ACM SIGKDD Int Conf Knowl Discov Data Min (KDD).2017:887\u2010895.","DOI":"10.1145\/3097983.3098118"},{"key":"e_1_2_10_26_1","first-page":"283","article-title":"Two\u2010stage federated phenotyping and patient representation learning","volume":"2019","author":"Liu D","year":"2019","journal-title":"NIH Public Access"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103291"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.2196\/24207"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13031911"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"DhavamaniM Alansary. A federated learning based approach for heart disease prediction.In 6th Int Conf Comput Methodol Commun (ICCMC).2022: 1117\u20101121.","DOI":"10.1109\/ICCMC53470.2022.9754119"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01506-3"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-07186-4"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13203166"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.860532"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/2599161"},{"key":"e_1_2_10_36_1","first-page":"1","article-title":"Federated learning based prediction of chronic kidney diseases","author":"Nandhini J","year":"2022","journal-title":"IEEE"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000117"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104881"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3597505"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/alz.065998"},{"key":"e_1_2_10_41_1","first-page":"2427","article-title":"Federated learning via conditional mutual learning for Alzheimer's disease classification on T1W MRI","volume":"2021","author":"Huang YL","year":"2021","journal-title":"IEEE"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110804"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23198272"},{"key":"e_1_2_10_44_1","first-page":"1362","article-title":"Fair and privacy\u2010preserving alzheimer's disease diagnosis based on spontaneous speech analysis via federated learning","volume":"2022","author":"Ali LiZ","year":"2022","journal-title":"IEEE"},{"key":"e_1_2_10_45_1","first-page":"264","volume-title":"A federated learning based alzheimer's disease prediction","author":"Suchitra S","year":"2024"},{"key":"e_1_2_10_46_1","volume-title":"Federated Domain Adaptation via Transformer for Multi\u2010Site Alzheimer's Disease Diagnosis","author":"Lei B","year":"2023"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/13682199.2023.2172524"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_10_49_1","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg SM","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_10_50_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq134"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1097\/ACM.0000000000002029"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-27856-1"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-biodatasci-122320-112352"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-211-89836-9_64"},{"key":"e_1_2_10_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104442"},{"key":"e_1_2_10_56_1","first-page":"2021","volume-title":"Identification of Parkinson PACE Subtypes and Repurposing Treatments through Integrative Analyses of Multimodal Clinical Progression, Neuroimaging, Genetic, and Transcriptomic Data","author":"Su C","year":"2021"},{"key":"e_1_2_10_57_1","doi-asserted-by":"crossref","unstructured":"BonawitzK IvanovV KreuterB et\u00a0al. Practical secure aggregation for privacy\u2010preserving machine learning.In Proc ACM SIGSAC Conf Comput Commun Secur (CCS).2017:1175\u20101191.","DOI":"10.1145\/3133956.3133982"},{"key":"e_1_2_10_58_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa341"},{"key":"e_1_2_10_59_1","doi-asserted-by":"publisher","DOI":"10.1038\/ejcn.2014.199"},{"key":"e_1_2_10_60_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.56.9.1188"},{"key":"e_1_2_10_61_1","article-title":"Cardiovascular risk factors promote brain hypoperfusion leading to cognitive decline and dementia","volume":"2012","author":"Jack","year":"2012","journal-title":"Cardiovasc Psychiatry Neurol"},{"key":"e_1_2_10_62_1","doi-asserted-by":"publisher","DOI":"10.1038\/nn0403-345"},{"key":"e_1_2_10_63_1","doi-asserted-by":"publisher","DOI":"10.1111\/jnc.15170"},{"key":"e_1_2_10_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00702-024-02769-z"},{"key":"e_1_2_10_65_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.322.7300.1447"},{"key":"e_1_2_10_66_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-1331.2012.03784.x"},{"key":"e_1_2_10_67_1","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9780890425596"},{"key":"e_1_2_10_68_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-022-01604-9"}],"container-title":["Alzheimer's &amp; Dementia"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/alz-journals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/alz.70128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T20:58:15Z","timestamp":1759957095000},"score":1,"resource":{"primary":{"URL":"https:\/\/alz-journals.onlinelibrary.wiley.com\/doi\/10.1002\/alz.70128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":67,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10.1002\/alz.70128"],"URL":"https:\/\/doi.org\/10.1002\/alz.70128","archive":["Portico"],"relation":{},"ISSN":["1552-5260","1552-5279"],"issn-type":[{"value":"1552-5260","type":"print"},{"value":"1552-5279","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]},"assertion":[{"value":"2025-01-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70128"}}